Optimal Design for Experiments with Potentially Failing Trials

Peter Hackl

doi:10.57938/dd289e52-f03a-4c9a-afb0-3b6bf912b18a

Optimal Design for Experiments with Potentially Failing Trials

Peter Hackl

Institute for Statistics and Mathematics

Publication: Working/Discussion Paper › WU Working Paper

48 Downloads (Pure)

Abstract

We discuss the problem of optimal allocation of the design points of an experiment for the case where the trials may fail with non-zero probability. Numerical results for D-optimal designs are given for estimating the coefficients of a polynomial regression. For small sample sizes these designs may deviate substantially from the corresponding designs in the case of certain response. They can be less efficient, but are less affected by failing trials. (author's abstract)

Original language	English
Place of Publication	Vienna
Publisher	Department of Statistics and Mathematics, WU Vienna University of Economics and Business
DOIs	https://doi.org/10.57938/dd289e52-f03a-4c9a-afb0-3b6bf912b18a
Publication status	Published - 1994

Publication series

Series	Forschungsberichte / Institut für Statistik
Number	39

WU Working Paper Series

Forschungsberichte / Institut für Statistik

Access to Document

10.57938/dd289e52-f03a-4c9a-afb0-3b6bf912b18aLicence: Unspecified

DocumentFinal published version, 456 KBLicence: Unspecified

Check availability

University Library Catalogue

Cite this

@techreport{dd289e52f03a4c9aafb03b6bf912b18a,

title = "Optimal Design for Experiments with Potentially Failing Trials",

abstract = "We discuss the problem of optimal allocation of the design points of an experiment for the case where the trials may fail with non-zero probability. Numerical results for D-optimal designs are given for estimating the coefficients of a polynomial regression. For small sample sizes these designs may deviate substantially from the corresponding designs in the case of certain response. They can be less efficient, but are less affected by failing trials. (author's abstract)",

author = "Peter Hackl",

year = "1994",

doi = "10.57938/dd289e52-f03a-4c9a-afb0-3b6bf912b18a",

language = "English",

series = "Forschungsberichte / Institut f{\"u}r Statistik",

number = "39",

publisher = "Department of Statistics and Mathematics, WU Vienna University of Economics and Business",

edition = "October 1994",

type = "WorkingPaper",

institution = "Department of Statistics and Mathematics, WU Vienna University of Economics and Business",

}

TY - UNPB

T1 - Optimal Design for Experiments with Potentially Failing Trials

AU - Hackl, Peter

PY - 1994

Y1 - 1994

N2 - We discuss the problem of optimal allocation of the design points of an experiment for the case where the trials may fail with non-zero probability. Numerical results for D-optimal designs are given for estimating the coefficients of a polynomial regression. For small sample sizes these designs may deviate substantially from the corresponding designs in the case of certain response. They can be less efficient, but are less affected by failing trials. (author's abstract)

AB - We discuss the problem of optimal allocation of the design points of an experiment for the case where the trials may fail with non-zero probability. Numerical results for D-optimal designs are given for estimating the coefficients of a polynomial regression. For small sample sizes these designs may deviate substantially from the corresponding designs in the case of certain response. They can be less efficient, but are less affected by failing trials. (author's abstract)

U2 - 10.57938/dd289e52-f03a-4c9a-afb0-3b6bf912b18a

DO - 10.57938/dd289e52-f03a-4c9a-afb0-3b6bf912b18a

M3 - WU Working Paper

T3 - Forschungsberichte / Institut für Statistik

BT - Optimal Design for Experiments with Potentially Failing Trials

PB - Department of Statistics and Mathematics, WU Vienna University of Economics and Business

CY - Vienna

ER -